Dual Adversarial Perturbators for Generating Rich Views in Recommendation Systems
The proposed AvoGCL model generates contrastive views of increasing difficulty through two trainable adversarial perturbators, which significantly outperforms state-of-the-art competitors in recommendation tasks.
RBoard: A Unified Platform for Reproducible and Reusable Benchmarking of Recommender Systems
RBoard is a novel framework that provides a comprehensive platform for benchmarking diverse recommendation tasks, with a primary focus on enabling fully reproducible and reusable experiments across various scenarios.
The Impact of Selection Bias on Preference Elicitation for Recommendation Systems
Selection bias in the preference elicitation stage can negatively impact the performance of subsequent item recommendations, but existing debiasing methods can help mitigate this effect.
Enhancing Multi-Behavior Recommendation through Behavior-Contextualized Item Preference Modeling
The core message of this paper is to introduce a novel approach, Behavior-Contextualized Item Preference Modeling (BCIPM), for multi-behavior recommendation. The proposed Behavior-Contextualized Item Preference Network (BIPN) discerns and learns users' specific item preferences within each behavior, considering only those preferences relevant to the target behavior for final recommendations, thereby significantly reducing noise from auxiliary behaviors.
Collaborative Filtering Based on Diffusion Models: Leveraging High-Order Connectivity for Accurate Recommendations
A novel diffusion model-based collaborative filtering method, CF-Diff, that effectively leverages high-order connectivity information to enhance recommendation accuracy.
Enhancing Probability-based Recommender Systems with Recklessness Regularization
Incorporating a recklessness regularization term in the learning process of probability-based recommender systems enables controlling the risk level of predictions, leading to improved quantity and quality of recommendations.
Sequential Recommendation for Optimizing Both Immediate User Engagement and Long-term Retention
The core message of this paper is to introduce DT4IER, a novel Decision Transformer-based framework that effectively balances the optimization of immediate user engagement and long-term user retention in sequential recommendation scenarios.
Large Language Models as Versatile End-to-End Recommenders: Overcoming the Limitations of Conventional Pipelined Systems
Large Language Models (LLMs) can be leveraged to seamlessly integrate multiple recommendation tasks, including recall, ranking, and re-ranking, within a unified end-to-end framework, eliminating the need for specialized models and enabling efficient handling of large-scale item sets.
Collaborative Information Filtering for Effective Cross-Domain Recommendation
The core message of this paper is that the distortion of user similarity relationships across domains is a key factor causing negative transfer in cross-domain recommendation, and the proposed Collaborative information regularized User Transformation (CUT) framework can effectively alleviate this issue by directly filtering irrelevant source-domain collaborative information.
Enhancing Recommender Systems: A Novel Negative Sampling Strategy to Mitigate False Negative Impact
A novel positive-dominated negative synthesizing (PDNS) strategy that mitigates the over-fitting issue caused by false negatives in hard negative sampling for recommender systems.
